agora inbox for pgsql-hackers@postgresql.orghelp / color / mirror / Atom feed
[PATCH v23 2/8] Row pattern recognition patch (parse/analysis). 324+ messages / 2 participants [nested] [flat]
* [PATCH v23 2/8] Row pattern recognition patch (parse/analysis). @ 2024-10-25 03:56 Tatsuo Ishii <ishii@postgresql.org> 0 siblings, 0 replies; 324+ messages in thread From: Tatsuo Ishii @ 2024-10-25 03:56 UTC (permalink / raw) --- src/backend/parser/parse_agg.c | 7 + src/backend/parser/parse_clause.c | 297 +++++++++++++++++++++++++++++- src/backend/parser/parse_expr.c | 6 + src/backend/parser/parse_func.c | 3 + 4 files changed, 312 insertions(+), 1 deletion(-) diff --git a/src/backend/parser/parse_agg.c b/src/backend/parser/parse_agg.c index efa730c167..a80263f90d 100644 --- a/src/backend/parser/parse_agg.c +++ b/src/backend/parser/parse_agg.c @@ -580,6 +580,10 @@ check_agglevels_and_constraints(ParseState *pstate, Node *expr) errkind = true; break; + case EXPR_KIND_RPR_DEFINE: + errkind = true; + break; + /* * There is intentionally no default: case here, so that the * compiler will warn if we add a new ParseExprKind without @@ -970,6 +974,9 @@ transformWindowFuncCall(ParseState *pstate, WindowFunc *wfunc, case EXPR_KIND_CYCLE_MARK: errkind = true; break; + case EXPR_KIND_RPR_DEFINE: + errkind = true; + break; /* * There is intentionally no default: case here, so that the diff --git a/src/backend/parser/parse_clause.c b/src/backend/parser/parse_clause.c index 4c97690908..a6d2f7f4ba 100644 --- a/src/backend/parser/parse_clause.c +++ b/src/backend/parser/parse_clause.c @@ -98,7 +98,14 @@ static WindowClause *findWindowClause(List *wclist, const char *name); static Node *transformFrameOffset(ParseState *pstate, int frameOptions, Oid rangeopfamily, Oid rangeopcintype, Oid *inRangeFunc, Node *clause); - +static void transformRPR(ParseState *pstate, WindowClause *wc, WindowDef *windef, + List **targetlist); +static List *transformDefineClause(ParseState *pstate, WindowClause *wc, WindowDef *windef, + List **targetlist); +static void transformPatternClause(ParseState *pstate, WindowClause *wc, + WindowDef *windef); +static List *transformMeasureClause(ParseState *pstate, WindowClause *wc, + WindowDef *windef); /* * transformFromClause - @@ -2956,6 +2963,10 @@ transformWindowDefinitions(ParseState *pstate, rangeopfamily, rangeopcintype, &wc->endInRangeFunc, windef->endOffset); + + /* Process Row Pattern Recognition related clauses */ + transformRPR(pstate, wc, windef, targetlist); + wc->winref = winref; result = lappend(result, wc); @@ -3823,3 +3834,287 @@ transformFrameOffset(ParseState *pstate, int frameOptions, return node; } + +/* + * transformRPR + * Process Row Pattern Recognition related clauses + */ +static void +transformRPR(ParseState *pstate, WindowClause *wc, WindowDef *windef, + List **targetlist) +{ + /* + * Window definition exists? + */ + if (windef == NULL) + return; + + /* + * Row Pattern Common Syntax clause exists? + */ + if (windef->rpCommonSyntax == NULL) + return; + + /* Check Frame option. Frame must start at current row */ + if ((wc->frameOptions & FRAMEOPTION_START_CURRENT_ROW) == 0) + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("FRAME must start at current row when row patttern recognition is used"))); + + /* Transform AFTER MACH SKIP TO clause */ + wc->rpSkipTo = windef->rpCommonSyntax->rpSkipTo; + + /* Transform AFTER MACH SKIP TO variable */ + wc->rpSkipVariable = windef->rpCommonSyntax->rpSkipVariable; + + /* Transform SEEK or INITIAL clause */ + wc->initial = windef->rpCommonSyntax->initial; + + /* Transform DEFINE clause into list of TargetEntry's */ + wc->defineClause = transformDefineClause(pstate, wc, windef, targetlist); + + /* Check PATTERN clause and copy to patternClause */ + transformPatternClause(pstate, wc, windef); + + /* Transform MEASURE clause */ + transformMeasureClause(pstate, wc, windef); +} + +/* + * transformDefineClause + * Process DEFINE clause and transform ResTarget into list of + * TargetEntry. + * + * XXX we only support column reference in row pattern definition search + * condition, e.g. "price". <row pattern definition variable name>.<column + * reference> is not supported, e.g. "A.price". + */ +static List * +transformDefineClause(ParseState *pstate, WindowClause *wc, WindowDef *windef, + List **targetlist) +{ + /* DEFINE variable name initials */ + static char *defineVariableInitials = "abcdefghijklmnopqrstuvwxyz"; + + ListCell *lc, + *l; + ResTarget *restarget, + *r; + List *restargets; + List *defineClause; + char *name; + int initialLen; + int i; + + /* + * If Row Definition Common Syntax exists, DEFINE clause must exist. (the + * raw parser should have already checked it.) + */ + Assert(windef->rpCommonSyntax->rpDefs != NULL); + + /* + * Check and add "A AS A IS TRUE" if pattern variable is missing in DEFINE + * per the SQL standard. + */ + restargets = NIL; + foreach(lc, windef->rpCommonSyntax->rpPatterns) + { + A_Expr *a; + bool found = false; + + if (!IsA(lfirst(lc), A_Expr)) + ereport(ERROR, + errmsg("node type is not A_Expr")); + + a = (A_Expr *) lfirst(lc); + name = strVal(a->lexpr); + + foreach(l, windef->rpCommonSyntax->rpDefs) + { + restarget = (ResTarget *) lfirst(l); + + if (!strcmp(restarget->name, name)) + { + found = true; + break; + } + } + + if (!found) + { + /* + * "name" is missing. So create "name AS name IS TRUE" ResTarget + * node and add it to the temporary list. + */ + A_Const *n; + + restarget = makeNode(ResTarget); + n = makeNode(A_Const); + n->val.boolval.type = T_Boolean; + n->val.boolval.boolval = true; + n->location = -1; + restarget->name = pstrdup(name); + restarget->indirection = NIL; + restarget->val = (Node *) n; + restarget->location = -1; + restargets = lappend((List *) restargets, restarget); + } + } + + if (list_length(restargets) >= 1) + { + /* add missing DEFINEs */ + windef->rpCommonSyntax->rpDefs = + list_concat(windef->rpCommonSyntax->rpDefs, restargets); + list_free(restargets); + } + + /* + * Check for duplicate row pattern definition variables. The standard + * requires that no two row pattern definition variable names shall be + * equivalent. + */ + restargets = NIL; + foreach(lc, windef->rpCommonSyntax->rpDefs) + { + restarget = (ResTarget *) lfirst(lc); + name = restarget->name; + + /* + * Add DEFINE expression (Restarget->val) to the targetlist as a + * TargetEntry if it does not exist yet. Planner will add the column + * ref var node to the outer plan's target list later on. This makes + * DEFINE expression could access the outer tuple while evaluating + * PATTERN. + * + * XXX: adding whole expressions of DEFINE to the plan.targetlist is + * not so good, because it's not necessary to evalute the expression + * in the target list while running the plan. We should extract the + * var nodes only then add them to the plan.targetlist. + */ + findTargetlistEntrySQL99(pstate, (Node *) restarget->val, + targetlist, EXPR_KIND_RPR_DEFINE); + + /* + * Make sure that the row pattern definition search condition is a + * boolean expression. + */ + transformWhereClause(pstate, restarget->val, + EXPR_KIND_RPR_DEFINE, "DEFINE"); + + foreach(l, restargets) + { + char *n; + + r = (ResTarget *) lfirst(l); + n = r->name; + + if (!strcmp(n, name)) + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("row pattern definition variable name \"%s\" appears more than once in DEFINE clause", + name), + parser_errposition(pstate, exprLocation((Node *) r)))); + } + restargets = lappend(restargets, restarget); + } + list_free(restargets); + + /* + * Create list of row pattern DEFINE variable name's initial. We assign + * [a-z] to them (up to 26 variable names are allowed). + */ + restargets = NIL; + i = 0; + initialLen = strlen(defineVariableInitials); + + foreach(lc, windef->rpCommonSyntax->rpDefs) + { + char initial[2]; + + restarget = (ResTarget *) lfirst(lc); + name = restarget->name; + + if (i >= initialLen) + { + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("number of row pattern definition variable names exceeds %d", + initialLen), + parser_errposition(pstate, + exprLocation((Node *) restarget)))); + } + initial[0] = defineVariableInitials[i++]; + initial[1] = '\0'; + wc->defineInitial = lappend(wc->defineInitial, + makeString(pstrdup(initial))); + } + + defineClause = transformTargetList(pstate, windef->rpCommonSyntax->rpDefs, + EXPR_KIND_RPR_DEFINE); + + /* mark column origins */ + markTargetListOrigins(pstate, defineClause); + + /* mark all nodes in the DEFINE clause tree with collation information */ + assign_expr_collations(pstate, (Node *) defineClause); + + return defineClause; +} + +/* + * transformPatternClause + * Process PATTERN clause and return PATTERN clause in the raw parse tree + */ +static void +transformPatternClause(ParseState *pstate, WindowClause *wc, + WindowDef *windef) +{ + ListCell *lc; + + /* + * Row Pattern Common Syntax clause exists? + */ + if (windef->rpCommonSyntax == NULL) + return; + + wc->patternVariable = NIL; + wc->patternRegexp = NIL; + foreach(lc, windef->rpCommonSyntax->rpPatterns) + { + A_Expr *a; + char *name; + char *regexp; + + if (!IsA(lfirst(lc), A_Expr)) + ereport(ERROR, + errmsg("node type is not A_Expr")); + + a = (A_Expr *) lfirst(lc); + name = strVal(a->lexpr); + + wc->patternVariable = lappend(wc->patternVariable, makeString(pstrdup(name))); + regexp = strVal(lfirst(list_head(a->name))); + + wc->patternRegexp = lappend(wc->patternRegexp, makeString(pstrdup(regexp))); + } +} + +/* + * transformMeasureClause + * Process MEASURE clause + * XXX MEASURE clause is not supported yet + */ +static List * +transformMeasureClause(ParseState *pstate, WindowClause *wc, + WindowDef *windef) +{ + if (windef->rowPatternMeasures == NIL) + return NIL; + + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("%s", "MEASURE clause is not supported yet"), + parser_errposition(pstate, exprLocation((Node *) windef->rowPatternMeasures)))); + return NIL; +} diff --git a/src/backend/parser/parse_expr.c b/src/backend/parser/parse_expr.c index ef0b560f5e..b30b9f2675 100644 --- a/src/backend/parser/parse_expr.c +++ b/src/backend/parser/parse_expr.c @@ -577,6 +577,7 @@ transformColumnRef(ParseState *pstate, ColumnRef *cref) case EXPR_KIND_COPY_WHERE: case EXPR_KIND_GENERATED_COLUMN: case EXPR_KIND_CYCLE_MARK: + case EXPR_KIND_RPR_DEFINE: /* okay */ break; @@ -1860,6 +1861,9 @@ transformSubLink(ParseState *pstate, SubLink *sublink) case EXPR_KIND_GENERATED_COLUMN: err = _("cannot use subquery in column generation expression"); break; + case EXPR_KIND_RPR_DEFINE: + err = _("cannot use subquery in DEFINE expression"); + break; /* * There is intentionally no default: case here, so that the @@ -3199,6 +3203,8 @@ ParseExprKindName(ParseExprKind exprKind) return "GENERATED AS"; case EXPR_KIND_CYCLE_MARK: return "CYCLE"; + case EXPR_KIND_RPR_DEFINE: + return "DEFINE"; /* * There is intentionally no default: case here, so that the diff --git a/src/backend/parser/parse_func.c b/src/backend/parser/parse_func.c index 9b23344a3b..4c482abb30 100644 --- a/src/backend/parser/parse_func.c +++ b/src/backend/parser/parse_func.c @@ -2658,6 +2658,9 @@ check_srf_call_placement(ParseState *pstate, Node *last_srf, int location) case EXPR_KIND_CYCLE_MARK: errkind = true; break; + case EXPR_KIND_RPR_DEFINE: + errkind = true; + break; /* * There is intentionally no default: case here, so that the -- 2.25.1 ----Next_Part(Fri_Oct_25_13_04_53_2024_648)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v23-0003-Row-pattern-recognition-patch-rewriter.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
* [PATCH v44 07/10] Split cluster.h to create repack_internal.h @ 2026-03-24 14:09 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 324+ messages in thread From: Álvaro Herrera @ 2026-03-24 14:09 UTC (permalink / raw) Most of the details of concurrent repack are only needed by pgoutput_repack; and they have a nasty effect on headers included by cluster.h (used by several high-profile places), so isolate that for cleanliness. Also, change_useless_for_repack() is better declared in decode.h. --- src/backend/commands/cluster.c | 128 ++++++++++-------- src/backend/postmaster/bgworker.c | 2 +- .../pgoutput_repack/pgoutput_repack.c | 13 +- src/include/commands/cluster.h | 57 +------- src/include/commands/repack_internal.h | 59 ++++++++ src/include/replication/decode.h | 4 + 6 files changed, 147 insertions(+), 116 deletions(-) create mode 100644 src/include/commands/repack_internal.h diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 75556cbdafb..2c3058ba10d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -59,6 +59,7 @@ #include "commands/cluster.h" #include "commands/defrem.h" #include "commands/progress.h" +#include "commands/repack_internal.h" #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" @@ -205,17 +206,11 @@ typedef struct DecodingWorkerShared char error_queue[FLEXIBLE_ARRAY_MEMBER]; } DecodingWorkerShared; -/* - * Generate worker's output file name. If relations of the same 'relid' happen - * to be processed at the same time, they must be from different databases and - * therefore different backends must be involved. (PID is already present in - * the fileset name.) - */ -static inline void -DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) -{ - snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); -} +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; /* * Backend-local information to control the decoding worker. @@ -241,6 +236,7 @@ static DecodingWorker *decoding_worker = NULL; */ volatile sig_atomic_t RepackMessagePending = false; +static LOCKMODE RepackLockLevel(bool concurrent); static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -298,12 +294,16 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); -static void start_decoding_worker(Oid relid); -static void stop_decoding_worker(void); + +static void start_repack_decoding_worker(Oid relid); +static void stop_repack_decoding_worker(void); static void repack_worker_internal(dsm_segment *seg); static void export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared); static Snapshot get_initial_snapshot(DecodingWorker *worker); +extern bool am_decoding_for_repack(void); +static void DecodingWorkerFileName(char *fname, Oid relid, uint32 seq); + static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -369,17 +369,8 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) parser_errposition(pstate, opt->location)); } - /* - * Determine the lock mode expected by cluster_rel(). - * - * In the exclusive case, we obtain AccessExclusiveLock right away to - * avoid lock-upgrade hazard in the single-transaction case. In the - * CONCURRENTLY case, the AccessExclusiveLock will only be used at the end - * of processing, supposedly for very short time. Until then, we'll have - * to unlock the relation temporarily, so there's no lock-upgrade hazard. - */ - lockmode = (params.options & CLUOPT_CONCURRENT) == 0 ? - AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lockmode = RepackLockLevel((params.options & CLUOPT_CONCURRENT) != 0); /* * If a single relation is specified, process it and we're done ... unless @@ -434,6 +425,12 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) "Repack", ALLOCSET_DEFAULT_SIZES); + /* + * Since we open a new transaction for each relation, we have to check + * that the relation still is what we think it is. + * + * In single-transaction CLUSTER, we don't need the overhead. + */ params.options |= CLUOPT_RECHECK; /* @@ -544,6 +541,22 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) MemoryContextDelete(repack_context); } +/* + * In the non-concurrent case, we obtain AccessExclusiveLock throughout the + * operation to avoid any lock-upgrade hazards. In the concurrent case, we + * grab ShareUpdateExclusiveLock (jsut like VACUUM) for most of the + * processing and only acquire AccessExclusiveLock at the end, to swap the + * relation -- supposedly for a short time. + */ +static LOCKMODE +RepackLockLevel(bool concurrent) +{ + if (concurrent) + return ShareUpdateExclusiveLock; + else + return AccessExclusiveLock; +} + /* * cluster_rel * @@ -583,25 +596,22 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, bool concurrent = ((params->options & CLUOPT_CONCURRENT) != 0); Oid ident_idx = InvalidOid; - /* - * The lock mode is AccessExclusiveLock for normal processing and - * ShareUpdateExclusiveLock for concurrent processing (so that SELECT, - * INSERT, UPDATE and DELETE commands work, but cluster_rel() cannot be - * called concurrently for the same relation). - */ - lmode = !concurrent ? AccessExclusiveLock : ShareUpdateExclusiveLock; + /* Determine the lock mode to use. */ + lmode = RepackLockLevel(concurrent); - /* There are specific requirements on concurrent processing. */ + /* + * Check some preconditions in the concurrent case. This also obtains the + * replica index OID. + */ if (concurrent) { /* - * Make sure we have no XID assigned, otherwise call of - * repack_setup_logical_decoding() can cause a deadlock. + * Make sure we're not in a transaction block. * - * The existence of transaction block actually does not imply that XID - * was already assigned, but it very likely is. We might want to check - * the result of GetCurrentTransactionIdIfAny() instead, but that - * would be less clear from user's perspective. + * The reason is that repack_setup_logical_decoding() could deadlock + * if there's an XID already assigned. It would be possible to run in + * a transaction block if we had no XID, but this restriction is + * simpler for users to understand and we don't lose anything. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); @@ -626,15 +636,11 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, RestrictSearchPath(); /* - * Since we may open a new transaction for each relation, we have to check - * that the relation still is what we think it is. + * Recheck that the relation is still what it was when we started. * - * If this is a single-transaction CLUSTER, we can skip these tests. We - * *must* skip the one on indisclustered since it would reject an attempt - * to cluster a not-previously-clustered index. - * - * XXX move [some of] these comments to where the RECHECK flag is - * determined? + * Note that it's critical to skip this in single-relation CLUSTER; + * otherwise, we would reject an attempt to cluster using a + * not-previously-clustered index. */ if (recheck && !cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, @@ -754,7 +760,7 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, * However it still seems a good practice to make sure that the * worker never survives the REPACK command. */ - stop_decoding_worker(); + stop_repack_decoding_worker(); } } PG_END_TRY(); @@ -1093,7 +1099,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * clustering index) and checking again if it's still eligible for * REPACK CONCURRENTLY. */ - start_decoding_worker(tableOid); + start_repack_decoding_worker(tableOid); /* * Wait until the worker has the initial snapshot and retrieve it. @@ -2538,7 +2544,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; /* keep compiler quiet */ } - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -3688,7 +3693,7 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) * contents to a new table. */ static void -start_decoding_worker(Oid relid) +start_repack_decoding_worker(Oid relid) { Size size; dsm_segment *seg; @@ -3779,7 +3784,7 @@ start_decoding_worker(Oid relid) * we need to stop it explicitly at least on ERROR in the launching backend. */ static void -stop_decoding_worker(void) +stop_repack_decoding_worker(void) { BgwHandleStatus status; @@ -3817,12 +3822,6 @@ stop_decoding_worker(void) decoding_worker = NULL; } -/* Is this process a REPACK worker? */ -static bool is_repack_worker = false; - -static pid_t backend_pid; -static ProcNumber backend_proc_number; - /* * See ParallelWorkerShutdown for details. */ @@ -3869,7 +3868,7 @@ RepackWorkerMain(Datum main_arg) /* * Join locking group - see the comments around the call of - * start_decoding_worker(). + * start_repack_decoding_worker(). */ if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) /* The leader is not running anymore. */ @@ -4039,6 +4038,18 @@ get_initial_snapshot(DecodingWorker *worker) return snapshot; } +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + bool IsRepackWorker(void) { @@ -4067,7 +4078,6 @@ void ProcessRepackMessages(void) { MemoryContext oldcontext; - static MemoryContext hpm_context = NULL; /* diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index f8a8d1681e9..9e876d55e27 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/parallel.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index 032fbd0e5b0..cc9ce615b18 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -13,7 +13,7 @@ #include "postgres.h" #include "access/detoast.h" -#include "commands/cluster.h" +#include "commands/repack_internal.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -176,7 +176,7 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - MemoryContext oldcxt; + MemoryContext oldcxt; BufFile *file; List *attrs_ext = NIL; int natt_ext; @@ -226,7 +226,10 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, slot_getsomeattrs(slot, i + 1); - /* This is a non-null varlena datum, but we only care if it's out-of-line */ + /* + * This is a non-null varlena datum, but we only care if it's + * out-of-line + */ varlen = (varlena *) DatumGetPointer(slot->tts_values[i]); if (!VARATT_IS_EXTERNAL(varlen)) continue; @@ -244,8 +247,8 @@ repack_store_change(LogicalDecodingContext *ctx, Relation relation, * attributes (those actually should never appear on disk), so * only TOASTed attribute can be seen here. * - * FIXME in what circumstances can an ONDISK attr appear? - * Why aren't these written separately? + * FIXME in what circumstances can an ONDISK attr appear? Why + * aren't these written separately? */ Assert(VARATT_IS_EXTERNAL_ONDISK(varlen)); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1c0ac3ab4f5..1528d34fa42 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -13,17 +13,12 @@ #ifndef CLUSTER_H #define CLUSTER_H -#include "nodes/execnodes.h" +#include <signal.h> + #include "nodes/parsenodes.h" #include "parser/parse_node.h" -#include "replication/decode.h" -#include "postmaster/bgworker.h" -#include "replication/logical.h" -#include "storage/buffile.h" #include "storage/lockdefs.h" -#include "storage/shm_mq.h" #include "utils/relcache.h" -#include "utils/resowner.h" /* flag bits for ClusterParams->options */ @@ -34,55 +29,14 @@ #define CLUOPT_ANALYZE 0x08 /* do an ANALYZE */ #define CLUOPT_CONCURRENT 0x10 /* allow concurrent data changes */ - /* options for CLUSTER */ typedef struct ClusterParams { bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; - -/* - * The following definitions are used by REPACK CONCURRENTLY. - */ - -/* - * Stored as a single byte in the output file. - */ -#define CHANGE_INSERT 'i' -#define CHANGE_UPDATE_OLD 'u' -#define CHANGE_UPDATE_NEW 'U' -#define CHANGE_DELETE 'd' -typedef char ConcurrentChangeKind; - -/* - * Logical decoding state. - * - * The output plugin uses it to store the data changes that it decodes from - * WAL while the table contents is being copied to a new storage. - */ -typedef struct RepackDecodingState -{ -#ifdef USE_ASSERT_CHECKING - /* The relation whose changes we're decoding. */ - Oid relid; -#endif - - /* Per-change memory context. */ - MemoryContext change_cxt; - - /* A tuple slot used to pass tuples back and forth */ - TupleTableSlot *slot; - - /* The current output file. */ - BufFile *file; -} RepackDecodingState; - extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; -extern bool IsRepackWorker(void); -extern void HandleRepackMessageInterrupt(void); -extern void ProcessRepackMessages(void); extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); @@ -104,8 +58,9 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, MultiXactId cutoffMulti, char newrelpersistence); -extern bool am_decoding_for_repack(void); -extern bool change_useless_for_repack(XLogRecordBuffer *buf); +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + -extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/commands/repack_internal.h b/src/include/commands/repack_internal.h new file mode 100644 index 00000000000..f90c973f5a0 --- /dev/null +++ b/src/include/commands/repack_internal.h @@ -0,0 +1,59 @@ +/*------------------------------------------------------------------------- + * + * repack_internal.h + * header for REPACK internals + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994-5, Regents of the University of California + * + * src/include/commands/repack_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef REPACK_INTERNAL_H +#define REPACK_INTERNAL_H + +#include "nodes/execnodes.h" +#include "replication/decode.h" +#include "postmaster/bgworker.h" +#include "replication/logical.h" +#include "storage/buffile.h" +#include "storage/shm_mq.h" +#include "utils/resowner.h" + +/* + * Stored as a single byte in the output file. + */ +#define CHANGE_INSERT 'i' +#define CHANGE_UPDATE_OLD 'u' +#define CHANGE_UPDATE_NEW 'U' +#define CHANGE_DELETE 'd' +typedef char ConcurrentChangeKind; + +/* + * Logical decoding state. + * + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. + */ +typedef struct RepackDecodingState +{ +#ifdef USE_ASSERT_CHECKING + /* The relation whose changes we're decoding. */ + Oid relid; +#endif + + /* Per-change memory context. */ + MemoryContext change_cxt; + + /* A tuple slot used to pass tuples back and forth */ + TupleTableSlot *slot; + + /* The current output file. */ + BufFile *file; +} RepackDecodingState; + + +extern void RepackWorkerMain(Datum main_arg); + +#endif /* REPACK_INTERNAL_H */ diff --git a/src/include/replication/decode.h b/src/include/replication/decode.h index 49f00fc48b8..02b5393474c 100644 --- a/src/include/replication/decode.h +++ b/src/include/replication/decode.h @@ -31,4 +31,8 @@ extern void logicalmsg_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf extern void LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *record); +/* in commands/cluster.c */ +extern bool change_useless_for_repack(XLogRecordBuffer *buf); + + #endif -- 2.47.3 --gwom7bl7ogtszo4k Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v44-0008-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 324+ messages in thread
end of thread, other threads:[~2026-03-24 14:09 UTC | newest] Thread overview: 324+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2024-10-25 03:56 [PATCH v23 2/8] Row pattern recognition patch (parse/analysis). Tatsuo Ishii <ishii@postgresql.org> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de> 2026-03-24 14:09 [PATCH v44 07/10] Split cluster.h to create repack_internal.h Álvaro Herrera <alvherre@kurilemu.de>
This inbox is served by agora; see mirroring instructions for how to clone and mirror all data and code used for this inbox